tungsten-logo
Sign In
Pikachu with Artisanal SDXL
artisanal-sdxl:alpha-1
evevalentine2017
evevalentine2017
·
Mar 6
373
Input
prompt
Specify things to see in the output
1 cyberpunk female pikachu, closeup shot, synthwave, geometric, art by Hilma af Klint
negative_prompt
Specify things to not see in the output
unaestheticXL2v10, vintage, retro, classic, boho, girl face
num_outputs
Number of output images
3
width
Output image width
768
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
1.2
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2337905100
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0.55
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
1
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
1
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
1
sampler
Sampler type
DPM++ 2M Karras
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
5
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
unaestheticXL2v10.safetensors
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
Output
https://files.tungsten.run/uploads/a81898a154fc4cf1be7cc58cd08db437/00000-2337905100.webp
https://files.tungsten.run/uploads/5bda003589664be6b60d05f4716dadba/00001-2337905101.webp
https://files.tungsten.run/uploads/ec18fa9715214c9681a94ec3c89ae79d/00002-2337905102.webp
Finished in 45.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: 1 cyberpunk female pikachu, closeup shot, synthwave, geometric, art by Hilma af Klint, <lora:add-detail-xl:1.2> Full negative prompt: unaestheticXL2v10, vintage, retro, classic, boho, girl face 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:02<01:08, 2.37s/it] 7%|▋ | 2/30 [00:03<00:42, 1.51s/it] 10%|█ | 3/30 [00:04<00:33, 1.23s/it] 13%|█▎ | 4/30 [00:05<00:28, 1.10s/it] 17%|█▋ | 5/30 [00:05<00:25, 1.03s/it] 20%|██ | 6/30 [00:06<00:23, 1.01it/s] 23%|██▎ | 7/30 [00:07<00:22, 1.04it/s] 27%|██▋ | 8/30 [00:08<00:20, 1.06it/s] 30%|███ | 9/30 [00:09<00:19, 1.08it/s] 33%|███▎ | 10/30 [00:10<00:18, 1.09it/s] 37%|███▋ | 11/30 [00:11<00:17, 1.09it/s] 40%|████ | 12/30 [00:12<00:16, 1.10it/s] 43%|████▎ | 13/30 [00:13<00:15, 1.10it/s] 47%|████▋ | 14/30 [00:14<00:14, 1.10it/s] 50%|█████ | 15/30 [00:15<00:13, 1.10it/s] 53%|█████▎ | 16/30 [00:15<00:12, 1.10it/s] 57%|█████▋ | 17/30 [00:16<00:11, 1.10it/s] 60%|██████ | 18/30 [00:17<00:10, 1.10it/s] 63%|██████▎ | 19/30 [00:18<00:09, 1.10it/s] 67%|██████▋ | 20/30 [00:19<00:09, 1.10it/s] 70%|███████ | 21/30 [00:20<00:08, 1.10it/s] 73%|███████▎ | 22/30 [00:21<00:07, 1.10it/s] 77%|███████▋ | 23/30 [00:22<00:06, 1.10it/s] 80%|████████ | 24/30 [00:23<00:05, 1.10it/s] 83%|████████▎ | 25/30 [00:24<00:04, 1.10it/s] 87%|████████▋ | 26/30 [00:24<00:03, 1.10it/s] 90%|█████████ | 27/30 [00:25<00:02, 1.10it/s] 93%|█████████▎| 28/30 [00:26<00:01, 1.10it/s] 97%|█████████▋| 29/30 [00:27<00:00, 1.10it/s] 100%|██████████| 30/30 [00:28<00:00, 1.10it/s] 100%|██████████| 30/30 [00:28<00:00, 1.05it/s] Decoding latents in cuda:0... done in 1.69s Move latents to cpu... done in 0.02s 0: 640x480 (no detections), 165.1ms Speed: 2.7ms preprocess, 165.1ms inference, 6.5ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x480 (no detections), 8.2ms Speed: 2.4ms preprocess, 8.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x480 (no detections), 9.0ms Speed: 2.4ms preprocess, 9.0ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 3 with 1st settings. Uploading outputs... Finished.
prompt
Specify things to see in the output
1 cyberpunk female pikachu, closeup shot, synthwave, geometric, art by Hilma af Klint
negative_prompt
Specify things to not see in the output
unaestheticXL2v10, vintage, retro, classic, boho, girl face
num_outputs
Number of output images
3
width
Output image width
768
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
1.2
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2337905100
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0.55
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
1
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
1
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
1
sampler
Sampler type
DPM++ 2M Karras
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
5
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
unaestheticXL2v10.safetensors
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/a81898a154fc4cf1be7cc58cd08db437/00000-2337905100.webp
https://files.tungsten.run/uploads/5bda003589664be6b60d05f4716dadba/00001-2337905101.webp
https://files.tungsten.run/uploads/ec18fa9715214c9681a94ec3c89ae79d/00002-2337905102.webp
Finished in 45.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: 1 cyberpunk female pikachu, closeup shot, synthwave, geometric, art by Hilma af Klint, <lora:add-detail-xl:1.2> Full negative prompt: unaestheticXL2v10, vintage, retro, classic, boho, girl face 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:02<01:08, 2.37s/it] 7%|▋ | 2/30 [00:03<00:42, 1.51s/it] 10%|█ | 3/30 [00:04<00:33, 1.23s/it] 13%|█▎ | 4/30 [00:05<00:28, 1.10s/it] 17%|█▋ | 5/30 [00:05<00:25, 1.03s/it] 20%|██ | 6/30 [00:06<00:23, 1.01it/s] 23%|██▎ | 7/30 [00:07<00:22, 1.04it/s] 27%|██▋ | 8/30 [00:08<00:20, 1.06it/s] 30%|███ | 9/30 [00:09<00:19, 1.08it/s] 33%|███▎ | 10/30 [00:10<00:18, 1.09it/s] 37%|███▋ | 11/30 [00:11<00:17, 1.09it/s] 40%|████ | 12/30 [00:12<00:16, 1.10it/s] 43%|████▎ | 13/30 [00:13<00:15, 1.10it/s] 47%|████▋ | 14/30 [00:14<00:14, 1.10it/s] 50%|█████ | 15/30 [00:15<00:13, 1.10it/s] 53%|█████▎ | 16/30 [00:15<00:12, 1.10it/s] 57%|█████▋ | 17/30 [00:16<00:11, 1.10it/s] 60%|██████ | 18/30 [00:17<00:10, 1.10it/s] 63%|██████▎ | 19/30 [00:18<00:09, 1.10it/s] 67%|██████▋ | 20/30 [00:19<00:09, 1.10it/s] 70%|███████ | 21/30 [00:20<00:08, 1.10it/s] 73%|███████▎ | 22/30 [00:21<00:07, 1.10it/s] 77%|███████▋ | 23/30 [00:22<00:06, 1.10it/s] 80%|████████ | 24/30 [00:23<00:05, 1.10it/s] 83%|████████▎ | 25/30 [00:24<00:04, 1.10it/s] 87%|████████▋ | 26/30 [00:24<00:03, 1.10it/s] 90%|█████████ | 27/30 [00:25<00:02, 1.10it/s] 93%|█████████▎| 28/30 [00:26<00:01, 1.10it/s] 97%|█████████▋| 29/30 [00:27<00:00, 1.10it/s] 100%|██████████| 30/30 [00:28<00:00, 1.10it/s] 100%|██████████| 30/30 [00:28<00:00, 1.05it/s] Decoding latents in cuda:0... done in 1.69s Move latents to cpu... done in 0.02s 0: 640x480 (no detections), 165.1ms Speed: 2.7ms preprocess, 165.1ms inference, 6.5ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x480 (no detections), 8.2ms Speed: 2.4ms preprocess, 8.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x480 (no detections), 9.0ms Speed: 2.4ms preprocess, 9.0ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 3 with 1st settings. Uploading outputs... Finished.